Dog bites in humans and estimating human rabies mortality in rabies endemic areas of Bhutan

Abstract

Background: Dog bites in humans are a public health problem worldwide. The issues of increasing stray dog populations, rabies outbreaks, and the risk of dogs biting humans have been frequently reported by the media in Bhutan. This study aimed to estimate the bite incidence and identify the risk factors for dog bites in humans, and to estimate human deaths from rabies in rabies endemic south Bhutan.

Methods: A hospital-based questionnaire survey was conducted during 2009-2010 among dog bites victims who visited three hospitals in Bhutan for anti-rabies vaccine injection. Decision tree modeling was used to estimate human deaths from rabies following dog bite injuries in two rabies endemic areas of south Bhutan.

Results: Three hundred and twenty four dog bite victims were interviewed. The annual incidence of dog bites differed between the hospital catchment areas: 869.8 (95% CI: 722.8-1022.5), 293.8 (240-358.2) and 284.8 (251.2-323) per 100,000 people in Gelephu, Phuentsholing and Thimphu, respectively. Males (62%) were more at risk than females (P<0.001). Children aged 5-9 years were bitten more than other age groups. The majority of victims (71%) were bitten by stray dogs. No direct fatal injury was reported. In two hospital areas (Gelephu and Phuentsholing) in south Bhutan the annual incidence of death from rabies was 3.14 (95% CI: 1.57-6.29) per 100,000 population. The decision tree model predicted an equivalent annual incidence of 4.67 (95% CI: 2.53-7.53) deaths/100,000 population at risk. In the absence of post exposure prophylaxis, the model predicted 19.24 (95% CI: 13.69-25.14) deaths/year in these two areas.

Conclusions: Increased educational awareness of people about the risk of dog bites and rabies is necessary, particularly for children in rabies endemic areas of Bhutan.

Figure 1. Decision tree model outlining the probability of rabies deaths.

The model is adapted from Cleaveland et al., 2002 (reference number 11). Probabilities (P1–P10) are defined in Table 4 and described in the methods section. The probability calculated represents the probability of death following the bite of a suspect rabid dog.

Figure 2. Predicted annual human deaths from rabies.

Deaths are predicted in Phuentsholing and Gelephu areas of south Bhutan in relation to rabies recognition probability (P1) and mean number of human rabies deaths reported, adapted from Cleaveland et al., 2002 (reference number 11).

Figure 3. Annual incidence of dog bites/100,000 population classified by age and gender.

Data is based on a survey of dog bite victims attending three hospitals (Jigme Dorji Wangchuk National Referral hospital, Phuentsholing General hospital, Gelephu Regional Referral hospital) in Bhutan, 2009–2010.

Figure 4. Anatomic location and severity of dog bite wounds.

Data is derived from victims attending three hospitals (Jigme Dorji Wangchuk National Referral hospital, Phuentsholing General hospital, Gelephu Regional Referral hospital) in Bhutan, 2009–2010 (the number in the figure indicates the number of bite victims).

Figure 5. Anatomic location of dog bite wounds according to age group.

Data is derived from victims attending three hospitals (Jigme Dorji Wangchuk National Referral hospital, Phuentsholing General hospital, Gelephu Regional Referral hospital) in Bhutan, 2009–2010 (the number in the figure indicates the number of bite victims). Age was categorized into the two groups indicated.